Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words starting with the "@" symbol

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the "@" symbol, often associated with references or handles in digital communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     circulation
    -0.73
     Gillespie
    -0.71
    ãĤº
    -0.71
     clerks
    -0.65
     Ortiz
    -0.63
     pes
    -0.63
    emonium
    -0.62
     Vaugh
    -0.61
    espie
    -0.61
     disl
    -0.60
    POSITIVE LOGITS
    #$
    1.41
    @@@@@@@@
    1.23
    realDonaldTrump
    1.19
    gmail
    1.15
    home
    1.02
    wcsstore
    0.94
    Home
    0.92
    example
    0.89
    @@@@
    0.88
    grad
    0.87
    Act Density 0.016%

    No Known Activations